전체 검색
AI 모델 2119
- Kimi-K2.7-Code-GGUF↗
unsloth
To run Kimi K2.7 Code in full precision lossless, run Q8 (UD-Q8_K_XL), which is 595GB and only 10GB bigger than Q4 (UD-Q4_K_XL). See our Kimi K2.7 Code guide for quantization analysis and instructions. Kimi K2.7 Code is a coding-focused agentic model built upon Kimi K2.6. With substantial improvements on real-world long-horizon coding tasks, it strengthens end-to-end task completion across complex software engineering workflows while improving token efficiency, reducing thinking-token usage by approximately 30% compared with Kimi K2.6. 1. **General Testing Details** - Unless stated otherwise, Kimi K2.7 Code and K2.6 were tested with thinking mode enabled via Kimi Code CLI at temperature = 1.0, top-p = 0.95, and a 262,144-token context length; GPT-5.5 ran in Codex with xhigh mode, and Opus 4.8 in Claude Code with xhigh mode. Aside from these differences, all benchmarks were evaluated under the same conditions. 2. **Coding Benchmarks** - Kimi Code Bench V2 is our in-house benchmark designed to evaluate coding agents on realistic tasks. It has diversed software engineering tasks across 10+ mainstream programming languages and a full production tech stack covering tasks from internal engineering use cases, production incidents, and real-world open-source projects, with emphasis on backend services, infrastructure, performance engineering, systems programming, security, frontend development, and ML/data engineering. - Program Bench evaluates code-generation agents by asking them to recreate a program’s behavior from only a compiled binary and its documentation. It spans 200 tasks, from small CLI tools to large systems like FFmpeg and SQLite. Submissions are judged against over 248,000 fuzz-generated behavioral tests. In each task, the agent is given an executable and its documentation, but no source code, decompilation, or internet access. It must choose its own implementation language, build the full program from scratch, and pass a behavioral test suite comparing its output against the original binary. - MLS-Bench evaluates whether AI systems can invent generalizable and scalable ML methods. MLS-Bench-Lite is the official 30-task subset of MLS-Bench, covering LLM pretraining and post-training, robotics, world models, computer vision, reinforcement learning, optimization, ML systems, AI for Science, and more. Agents are given 5 hours to explore before submitting
- Depth-Anything-V2-Metric-Indoor-Base-hf↗
depth-anything
This model represents a fine-tuned version of Depth Anything V2 for indoor metric depth estimation using the synthetic Hypersim datasets. Depth Anything V2 was introduced in the paper of the same name by Lihe Yang et al. It uses the same architecture as the original Depth Anything release but employs synthetic data and a larger capacity teacher model to achieve much finer and robust depth predictions. This fine-tuned version for metric depth estimation was first released in this repository. **Six metric depth models** of three scales for indoor and outdoor scenes, respectively, were released and are available:
- unispeech-sat-base-100h-libri-ft↗
Microsoft
A unispeech-sat-base model that was fine-tuned on 100h hours of Librispeech on 16kHz sampled speech audio. When using the model make sure that your speech input is also sampled at 16Khz. Authors: Sanyuan Chen, Yu Wu, Chengyi Wang, Zhengyang Chen, Zhuo Chen, Shujie Liu, Jian Wu, Yao Qian, Furu Wei, Jinyu Li, Xiangzhan Yu **Abstract** *Self-supervised learning (SSL) is a long-standing goal for speech processing, since it utilizes large-scale unlabeled data and avoids extensive human labeling. Recent years witness great successes in applying self-supervised learning in speech recognition, while limited exploration was attempted in applying SSL for modeling speaker characteristics. In this paper, we aim to improve the existing SSL framework for speaker representation learning. Two methods are introduced for enhancing the unsupervised speaker information extraction. First, we apply the multi-task learning to the current SSL framework, where we integrate the utterance-wise contrastive loss with the SSL objective function. Second, for better speaker discrimination, we propose an utterance mixing strategy for data augmentation, where additional overlapped utterances are created unsupervisely and incorporate during training. We integrate the proposed methods into the HuBERT framework. Experiment results on SUPERB benchmark show that the proposed system achieves state-of-the-art performance in universal representation learning, especially for speaker identification oriented tasks. An ablation study is performed verifying the efficacy of each proposed method. Finally, we scale up training dataset to 94 thousand hours public audio data and achieve further performance improvement in all SUPERB tasks..*
- Mistral-7B-Instruct-v0.2↗
Mistral AI
> [!TIP] > PRs to correct the `transformers` tokenizer so that it gives 1-to-1 the same results as the `mistral_common` reference implementation are very welcome! The Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.2. Mistral-7B-v0.2 has the following changes compared to Mistral-7B-v0.1 - 32k context window (vs 8k context in v0.1) - Rope-theta = 1e6 - No Sliding-Window Attention
- sopro-v2-turbo↗
samuel-vitorino
> **Compatibility:** Current model artifacts require `sopro>=2.2.0` or `@soprotts/onnx-web>=0.3.0`; upgrade with `pip install -U sopro` or `npm install @soprotts/onnx-web@latest`. Sopro (from the Portuguese word for "breath/blow") is a lightweight voice-cloning text-to-speech model family. This repo ships **sopro-v2-turbo**, a 120M-parameter open model that streams, runs comfortably on a laptop CPU or in the browser, and reaches SOTA-level intelligibility against much larger systems. The full story, evaluations, and audio samples are in the blog post. - **120M parameters** - **English, European Portuguese, French, and German** - **Streaming** with ~300 ms time-to-first-audio on a laptop CPU - **Zero-shot voice cloning** from 5-20 seconds of reference audio - **0.24 RTF offline / 0.21 RTF streaming** on an M3 CPU, 0.07 RTF on an H100 - **Runs in the browser** via an ONNX runtime
- chronos-t5-mini↗
autogluon
🚀 **Update Feb 14, 2025**: Chronos-Bolt & original Chronos models are now available on Amazon SageMaker JumpStart! Check out the tutorial notebook to learn how to deploy Chronos endpoints for production use in a few lines of code. 🚀 **Update Nov 27, 2024**: We have released Chronos-Bolt⚡️ models that are more accurate (5% lower error), up to 250 times faster and 20 times more memory-efficient than the original Chronos models of the same size. Check out the new models here. Chronos is a family of **pretrained time series forecasting models** based on language model architectures. A time series is transformed into a sequence of tokens via scaling and quantization, and a language model is trained on these tokens using the cross-entropy loss. Once trained, probabilistic forecasts are obtained by sampling multiple future trajectories given the historical context. Chronos models have been trained on a large corpus of publicly available time series data, as well as synthetic data generated using Gaussian processes.
- Qwen3.8-27B-SmoothQuant-W8A8-INT8↗
Freaksterz
**v3 (`main`, 2026-09-03):** mean full-vocab KLD vs BF16 **0.00556** — lower than the official `Qwen/Qwen3.8-27B-FP8` on the same harness (0.00584) — and the stock **DFlash2 drafter works unchanged** (acceptance length 4.34, identical to a W8A16 target). No residual-stream rotation. 288 of 400 Linear modules run INT8×INT8 on Ampere tensor cores; prefill is 1.42× a W8A16 checkpoint of the same model. Previous revisions stay available: `v2-rotated` (KLD 0.01098, rotation-based; **breaks DFlash2**, MTP only) and `v1-smoothquant-rtn` (0.01414, DFlash2-compatible). If you are here because DFlash2 gave 0% acceptance on v2: `main` fixes it. Teacher-forced full-vocab KLD, BF16 reference captured offline (transformers), candidates served through vLLM (so INT8 *activation* rounding is included). 240 × 512-token WikiText-2 windows = 122,640 positions, top-K 512 with reported tail bound. "Floor-free" is the paired estimator that removes the truncation floor (see `eval/` in the repo).
- open-vakgyata↗
onecxi
**Model Overview:** open-vakgyata is an open-source language identification model capable of detecting and classifying indian languages from speech inputs. **Supported Languages:** | Language | Code | |----------------------|-------| | English (India) | en-IN | | Hindi | hi-IN | | Odia | or-IN | | Bengali | bn-IN | | Tamil | ta-IN | | Telugu | te-IN | | Kannada | kn-IN | | Malayalam | ml-IN | | Marathi | mr-IN | | Gujarati | gu-IN | **Specification** - Supported Sampling Rate: 16000 - Recomonded Audio Format: 16kHz, 16bit PCM
- InternVL3-78B↗
OpenGVLab
We introduce InternVL3, an advanced multimodal large language model (MLLM) series that demonstrates superior overall performance. Compared to InternVL 2.5, InternVL3 exhibits superior multimodal perception and reasoning capabilities, while further extending its multimodal capabilities to encompass tool usage, GUI agents, industrial image analysis, 3D vision perception, and more. Additionally, we compare InternVL3 with Qwen2.5 Chat models, whose corresponding pre-trained base models are employed as the initialization of the langauge component in InternVL3. Benefitting from Native Multimodal Pre-Training, the InternVL3 series achieves even better overall text performance than the Qwen2.5 series. As shown in the following figure, InternVL3 retains the same model architecture as InternVL 2.5 and its predecessors, InternVL 1.5 and 2.0, following the "ViT-MLP-LLM" paradigm. In this new version, we integrate a newly incrementally pre-trained InternViT with various pre-trained LLMs, including InternLM 3 and Qwen 2.5, using a randomly initialized MLP projector. As in the previous version, we applied a pixel unshuffle operation, reducing the number of visual tokens to one-quarter of the original. Besides, we adopted a similar dynamic resolution strategy as InternVL 1.5, dividing images into tiles of 448×448 pixels. The key difference, starting from InternVL 2.0, is that we additionally introduced support for multi-image and video data.
- PP-OCRv6_medium_det_onnx↗
PaddlePaddle
PP-OCRv6: From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks **🔥 Official Website** **📝 Technical Report** PP-OCRv6 is a lightweight OCR system that combines architectural innovation with data-centric optimization. It redesigns the backbone, detection neck, and recognition neck around a unified MetaFormer-style building block with structural reparameterization. Three model tiers (medium, small, tiny) share the same block primitives, covering deployment scenarios from server to edge.